zeroshotGPU / examples /parse_pdf.py
Arjunvir Singh
Initial commit: zeroshotGPU MVP with full eval surface
db06ffa
"""Parse one PDF with the MVP pipeline."""
from __future__ import annotations
import argparse
from zsgdp import parse_document
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument("input")
parser.add_argument("output")
args = parser.parse_args()
parsed = parse_document(args.input, args.output)
print(
f"score={parsed.quality_report.score:.2f} "
f"elements={len(parsed.elements)} tables={len(parsed.tables)} "
f"figures={len(parsed.figures)} chunks={len(parsed.chunks)}"
)
return 0
if __name__ == "__main__":
raise SystemExit(main())